CN112953781B - Virtual service fault recovery method and device based on particle swarm under network slice - Google Patents
Virtual service fault recovery method and device based on particle swarm under network slice Download PDFInfo
- Publication number
- CN112953781B CN112953781B CN202110353228.9A CN202110353228A CN112953781B CN 112953781 B CN112953781 B CN 112953781B CN 202110353228 A CN202110353228 A CN 202110353228A CN 112953781 B CN112953781 B CN 112953781B
- Authority
- CN
- China
- Prior art keywords
- representing
- node
- resource
- link
- recovery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000002245 particle Substances 0.000 title claims abstract description 177
- 238000011084 recovery Methods 0.000 title claims abstract description 174
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 75
- 238000005457 optimization Methods 0.000 claims abstract description 47
- 230000006870 function Effects 0.000 claims description 18
- 238000010276 construction Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012545 processing Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000013468 resource allocation Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000009827 uniform distribution Methods 0.000 description 3
- 239000013598 vector Substances 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/06—Management of faults, events, alarms or notifications
- H04L41/0654—Management of faults, events, alarms or notifications using network fault recovery
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Data Exchanges In Wide-Area Networks (AREA)
Abstract
The invention discloses a virtual service fault recovery method based on particle swarm under network slicing, which comprises the following steps: constructing a fault recovery model in a network slicing environment according to bottom node resources and bottom link resources of a bottom network in a basic network; constructing a particle swarm optimization algorithm model according to the fault recovery model; and solving the fault recovery model by adopting the particle swarm optimization algorithm model to obtain a virtual service fault recovery strategy. The invention aims at maximizing the quantity of the recovered fault services, adopts the particle swarm optimization algorithm to solve the problem that the quantity of the recovered fault services is less under the constraint condition that available resources are limited.
Description
Technical Field
The present invention relates to the field of fault management technologies of electric power communication networks, and in particular, to a method, an apparatus, a terminal device, and a computer readable storage medium for recovering a virtual service fault based on a particle swarm under a network slice.
Background
In the network slicing environment, the base network is divided into an underlay network and a virtual network. The underlying network includes underlying nodes and underlying links. The virtual network includes virtual nodes and virtual links. The service provider builds a virtual network by renting resources of the underlying network, thereby rapidly providing specific virtual network services to the target user. As the number of virtual network services carried on the underlying network increases after the network is sliced, if the underlying network fails, more virtual network services will be unavailable.
At present, many researches have been carried out, but with the rapid development of networks, the scale of the core network is also larger and larger, the probability of network faults is also larger and larger, and how to recover as many virtual network services as possible under the constraint of limited resources becomes a problem to be solved urgently.
Disclosure of Invention
The purpose of the invention is that: the virtual service fault recovery method and device based on the particle swarm under the network slice can solve the problem that the number of recovered fault services is small under the constraint condition that available resources are limited.
In order to achieve the above object, the present invention provides a virtual service fault recovery method based on a particle swarm under a network slice, including:
constructing a fault recovery model in a network slicing environment according to bottom node resources and bottom link resources of a bottom network in a basic network;
constructing a particle swarm optimization algorithm model according to the fault recovery model;
and solving the fault recovery model by adopting the particle swarm optimization algorithm model to obtain a virtual service fault recovery strategy.
Further, the constructing a fault recovery model in the network slicing environment according to the bottom node resources and the bottom link resources of the bottom network in the base network specifically includes:
Constructing a resource constraint condition of bottom node recovery, and adopting the following formula:
wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a set of failed nodes that need to be restored, +.>A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When->When the value is 1, it indicates that the failed node m has been successfully recovered, when +.>When the value is 0, the fault node m is not successfully recovered, re n Representing the total node recovery resource amount;
constructing a constraint condition of the recovery resources of the bottom link, and adopting the formula:
wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e Indicating a failure requiring recoveryIs a set of link components->Identification indicating whether the failed link mn was successfully recovered, with a value of +.>When (when)When the value is 1, it indicates that the failed link mn is successfully recovered, when +.>When the value is 0, the failure link mn is not recovered successfully, re e Representing the total link recovery resource amount;
constructing a constraint condition of allocating resources by the bottom layer node, and adopting the formula:
wherein, representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node- >Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The number of computing resources occupied by the virtual service which can still be borne after the fault occurs;
constructing a constraint condition of the allocation resources of the bottom link, and adopting the following formula:
wherein, representing recovered faulty traffic +>The amount of bandwidth resources allocated to the underlying link mn is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link mn, B mn Representing the total bandwidth resource amount of the underlying link mn, B g The bandwidth resource quantity occupied by the virtual service which can still be carried after the bottom link mn fails is represented;
establishing an objective function of a fault recovery model according to the resource constraint condition of the bottom node recovery, the resource constraint condition of the bottom link recovery, the resource constraint condition of the bottom node allocation and the resource constraint condition of the bottom link allocation:
wherein, indicating the number of successfully restored virtual network traffic, +.>Representing a failed set of virtual network traffic, +.>Representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When->When the value is 1, the virtual business is represented>Is successfully recovered when- >When the value is 0, the virtual business is represented>Is not successfully recovered.
Further, the particle swarm optimization algorithm model is constructed according to the fault recovery model, specifically:
and optimizing the position parameters of the particles and the speed parameters of the particles in the particle swarm algorithm to obtain a particle swarm optimization algorithm model, wherein the position parameters of the particles represent a resource recovery scheme, and the speed of the particles represent an optimization strategy of the resource recovery scheme.
Further, the particle swarm optimization algorithm model is adopted to solve the fault recovery model, so as to obtain a virtual service fault recovery strategy, which is specifically as follows:
constructing a two-layer association model of the fault resource and the virtual service according to the mapping relation of the fault resource and the virtual service;
building a binary string X of a failed resource i Each bit indicating whether the current network resource is restored;
initializing parameters, wherein the parameters comprise: iteration number MG, particle swarm size N, initial position X of randomly generated particles i And initial velocity V of randomly generated particles i ;
Calculating an initial position of the particle, comprising: calculating fitness function value f (X) of each particle position i ) And will be the optimal initial position X i Set as global optimum initial position X gb The initial position X of each particle i Set to the individual optimal initial position X pb ;
Updating the particle speed, the particle position, the global optimal initial position and the individual optimal initial position;
judging whether a preset end condition is reached, if so, outputting the optimal X i If not, returning to the execution step to update the particle speed, the particle position, the global optimal initial position and the individual optimal initial position.
The embodiment of the invention also provides a virtual service fault recovery device based on the particle swarm under the network slice, which comprises the following steps: a fault construction module, an algorithm construction module and a processing module, wherein,
the fault construction module is used for constructing a fault recovery model in a network slicing environment according to the bottom node resources and the bottom link resources of the bottom network in the basic network;
the algorithm construction module is used for constructing a particle swarm optimization algorithm model according to the fault recovery model;
and the processing module is used for solving the fault recovery model by adopting the particle swarm optimization algorithm model to obtain a virtual service fault recovery strategy.
Further, the fault construction module is specifically configured to:
Constructing a resource constraint condition of bottom node recovery, and adopting the following formula:
wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a set of failed nodes that need to be restored, +.>A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When->When the value is 1, it indicates that the failed node m has been successfully recovered, when +.>When the value is 0, the fault node m is not successfully recovered, re n Representing the total node recovery resource amount;
constructing a constraint condition of the recovery resources of the bottom link, and adopting the formula:
wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e A set representing the failed link composition requiring restoration, +.>Identification indicating whether the failed link mn was successfully recovered, with a value of +.>When (when)When the value is 1, it indicates that the failed link mn is successfully recovered, when +.>When the value is 0, the failure link mn is not recovered successfully, re e Representing the total link recovery resource amount;
constructing a constraint condition of allocating resources by the bottom layer node, and adopting the formula:
wherein, representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node- >Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The number of computing resources occupied by the virtual service which can still be borne after the fault occurs;
constructing a constraint condition of the allocation resources of the bottom link, and adopting the following formula:
wherein, representing recovered faulty traffic +>The amount of bandwidth resources allocated to the underlying link mn is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link mn, B mn Representing the total bandwidth resource amount of the underlying link mn, B g The bandwidth resource quantity occupied by the virtual service which can still be carried after the bottom link mn fails is represented;
establishing an objective function of a fault recovery model according to the resource constraint condition of the bottom node recovery, the resource constraint condition of the bottom link recovery, the resource constraint condition of the bottom node allocation and the resource constraint condition of the bottom link allocation:
wherein, indicating the number of successfully restored virtual network traffic, +.>Representing a failed set of virtual network traffic, +.>Representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When->When the value is 1, the virtual business is represented>Is successfully recovered when- >When the value is 0, the virtual business is represented>Is not successfully recovered.
Further, the algorithm construction module is specifically configured to:
and optimizing the position parameters of the particles and the speed parameters of the particles in the particle swarm algorithm to obtain a particle swarm optimization algorithm model, wherein the position parameters of the particles represent a resource recovery scheme, and the speed of the particles represent an optimization strategy of the resource recovery scheme.
Further, the processing module is specifically configured to:
constructing a two-layer association model of the fault resource and the virtual service according to the mapping relation of the fault resource and the virtual service;
building a binary string X of a failed resource i Each bit indicating whether the current network resource is restored;
initializing parameters, wherein the parameters comprise: iteration number MG, particle swarm size N, initial position X of randomly generated particles i And initial velocity V of randomly generated particles i ;
Calculating an initial position of the particle, comprising: calculating fitness function value f (X) of each particle position i ) And will be the optimal initial position X i Set as global optimum initial position X gb The initial position X of each particle i Set to the individual optimal initial position X pb ;
Updating the particle speed, the particle position, the global optimal initial position and the individual optimal initial position;
Judging whether a preset end condition is reached, if so, outputting the optimal X i If not, returning to the execution step to update the particle speed, the particle position, the global optimal initial position and the individual optimal initial position.
The embodiment of the invention also provides a computer terminal device, which comprises: one or more processors; a memory coupled to the processor for storing one or more programs; the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for particle swarm-based virtual traffic failure recovery under network slice as described in any of the preceding claims.
The embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which is characterized in that the computer program, when executed by a processor, implements the virtual service fault recovery method based on the particle swarm under the network slice as described in any one of the above.
Compared with the prior art, the virtual service fault recovery method and device based on the particle swarm under the network slice have the beneficial effects that:
the invention aims at maximizing the recovery fault business quantity and adopts a particle swarm optimization algorithm to solve. In the aspect of comparing indexes, the invention uses two indexes of fault recovery rate and user satisfaction to evaluate, and compared with the existing fault recovery method, the invention can find the optimal recovery strategy by running in the experimental simulation environment, and can recover more failed bottom network resources, thereby recovering more failed virtual network services.
Drawings
Fig. 1 is a schematic flow chart of a virtual service fault recovery method based on a particle swarm under a network slice according to an embodiment of the present invention;
FIG. 2 is a schematic diagram illustrating the comparison of a virtual service failure recovery rate and a prior art failure recovery rate according to an embodiment of the present invention;
FIG. 3 is a schematic diagram illustrating the effect of total recovery resources on user satisfaction according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a virtual service fault recovery device based on a particle swarm under a network slice according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be understood that the step numbers used herein are for convenience of description only and are not limiting as to the order in which the steps are performed.
It is to be understood that the terminology used in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
The terms "comprises" and "comprising" indicate the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
The term "and/or" refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations.
First embodiment of the present invention:
as shown in fig. 1, the method for recovering virtual service faults based on particle swarm under network slicing according to the embodiment of the invention at least comprises the following steps:
s101, constructing a fault recovery model in a network slicing environment according to bottom node resources and bottom link resources of a bottom network in a basic network;
in the network slicing environment, the base network is divided into an underlying network and a virtual network. Underlying network usage G S =(N S ,E S ) Representation, where N S Representing a set of underlying nodes, each underlying nodeHaving computing resource properties, use->And (3) representing. E (E) S Representing the set of underlying links, each underlying link +.>Having bandwidth resource attributes, usageAnd (3) representing. Virtual network usage G V =(N V ,E V ) And (3) representing. Wherein N is V Representing a set of virtual nodes, each virtual nodeComputing resource amount usage requiring application to underlying nodes>And (3) representing. E (E) V Representing a set of virtual links, each virtual link +.>Bandwidth resource amount usage requiring application to the underlying link>And (3) representing. />
The service provider applies for resources to the underlying network provider using G V =(N V ,E V ) The amount of resources needed is described. Underlying network service provider provides virtual network servicesUse G when a vendor provides resources V ↓G S The resource allocation situation is described. Wherein, the bottom layer nodeIs virtual node->Allocate resources, use->And (3) representing. Bottom layer Path->For virtual link->Allocate resources, use->And (3) representing. Bottom layer Path->And the path is a bottom path formed by connecting a plurality of bottom links, and two end nodes of the path are two bottom nodes mapped by two virtual endpoints of the virtual link. After renting the virtual network, the virtual network service provider can deploy personalized services to provide services for the end user. The invention mainly researches the end-to-end virtual network service and uses->Representing slave virtual nodes->To virtual node->End-to-end traffic of (a) is provided.
The difficulty with the problem of failure recovery is how to use a finiteAnd recovering the fault resources as much as possible by recovering the quantity of the recovery resources, thereby realizing the maximization of recovery service. Re is used separately for a limited number of recovery resources, including total node recovery resources, total link recovery resources n And Re (Re) e And (3) representing.
For the resource limitation problem of the underlying node recovery, it can be described using equation (1). The meaning of the formula is that the total amount of recovery resources occupied by the underlying nodes that are successfully recovered cannot exceed the total amount of node recovery resources. Wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a collection of failed nodes that need to be restored. />A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When the value is 1, it indicates that the failed node m has been successfully recovered. When the value is 0, it indicates that the failed node m is not successfully recovered.
For the resource limitation problem of the underlying link recovery, it can be described using equation (2). The meaning of the formula is that the total amount of recovery resources occupied by the underlying links that are successfully recovered cannot exceed the total amount of link recovery resources. Wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e Representing the set of failed link components that need to be recovered.Representing faultsIdentification of whether link mn was successfully restored, taking the value +.>When the value is 1, this indicates that the failed link mn was successfully recovered. When the value is 0, it indicates that the failed link mn is not successfully recovered.
When the failed bottom node and the bottom link are successfully recovered, the method can be used for recovering the virtual network service. When the virtual network service is restored, the bottom node resources and the bottom link resources occupied by the restoration service cannot exceed the free resource quantity of the bottom node resources and the bottom link resources. In terms of resource constraint of bottom node allocation, the bottom nodeIs calculated using equation (3). The formula indicates that the amount of resources of the bottom node occupied by the restored service cannot exceed the resource limit of the bottom node after restoration. Wherein (1)>Representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node->Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The amount of computing resources occupied by the virtual traffic that is still loadable after the failure.
In terms of resource allocation constraints of the underlying linksIs calculated using equation (4). The formula indicates that the amount of resources of the underlying link occupied by the restored traffic cannot exceed the resource limit of the underlying link after restoration. Wherein (1)>Representing recovered faulty traffic + >The amount of bandwidth resources allocated to it by the underlying link (mn) is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link (mn), B mn Representing the total bandwidth resource amount of the underlying links (mn), B g Representing the amount of bandwidth resources occupied by virtual traffic that is still loadable after the underlying link (mn) fails.
Based on the above, the objective function of the virtual network service fault recovery problem is defined as a formula (5), the constraint condition is a formula (1-4), and the meaning of the formula is that the recovery quantity of the failure service is maximized, namely, as many virtual network services as possible are recovered under the condition of limited resources. In the formula (i),indicating the number of successfully restored virtual network traffic, +.>Representing a failed set of virtual network traffic. />Representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When the value is 1, virtual service is indicated>Is successfully recovered. When the value is 0, it indicates virtual traffic +.>Is not successfully recovered.
S102, constructing a particle swarm optimization algorithm model according to the fault recovery model;
from the objective function and its constraint, the solution requiring the solution optimization is an NP-hard problem. In order to obtain an optimal solution, the particle swarm optimization algorithm is adopted for solving. The particle swarm optimization algorithm is an intelligent algorithm for guiding searching the optimal solution through mutual learning among particles. Two key parameters of particle swarm optimization algorithms are the position of the particles and the velocity of the particles.
In the present invention, the location of a particle refers to a resource recovery scheme. The velocity of a particle refers to the velocity of the particle from oneThe process of moving the particle position to a more optimal particle position. UsingThe vector representing the D particle positions is defined as the i-th recovery scheme. Wherein D represents a fault underlying node F which needs to be recovered n And failure of the underlying link F e A set of structures. Every element in the collection +.>And indicating whether the current failure bottom layer resource is recovered or not, wherein the value is a binary value. When the value is 1, the recovery of the current failure bottom layer resource is indicated. When the value is 0, the current failure bottom layer resource is not recovered.
Particle velocity is used to represent an optimization strategy for a resource recovery scheme, using vectorsAnd (3) representing. Wherein the vector element->Indicating whether the recovery state of the jth network resource that needs to be recovered needs to be changed. When->Indicating that a change is required. When->No changes are required for the representation. X is used when each particle moves pb Representing its historically optimal location, X is used gb Representing the location of global history optima.
In the particle swarm optimization algorithm, three operations of addition, subtraction and multiplication of particles are generally adopted to optimize the recovery scheme. Particle addition operation Representing an optimization strategy for computing a recovery scheme. The calculation method is shown in formula (6). Wherein P is i And P j Represents the probability of taking an existing recovery scheme, and P i +p=1 (0.ltoreq.p.ltoreq.1). The representation is used when the probability of a certain recovery scheme is uncertain. For example, a->The first one represents that the recovery scheme of the current failure resource is to take 0 with a probability of 0.1 and take 1 with a probability of 0.9.
The subtraction is denoted with Θ for comparing the difference between the two recovery schemes. The calculation method is shown in formula (7). The calculation method is to compare the values in each dimension. If equal, the subtraction result is 1. If not, the result of the subtraction is 0. For example, (1, 0) Θ (1,0,1,0,1) = (1,0,0,1,0).
X i And X j Difference = X i ΘX j (7)
Multiplication operation usesAnd means for calculating a new more optimal solution. The calculation method is shown in formula (8).
For example, the number of the cells to be processed,indicating that the second one of the recovery schemes requires adjustment.
Based on the calculation method, an optimization method of the particle position can be obtained as formula (9), and an optimization formula of the particle speed can be obtained as formula (10).
And S103, solving the fault recovery model by adopting the particle swarm optimization algorithm model to obtain a virtual service fault recovery strategy.
It should be noted that, through the process analysis of the particle swarm algorithm, the virtual business fault recovery algorithm (Virtual Service Failure Recovery Algorithm based on Particle Swarm, vsfraohw) based on the particle swarm provided by the present invention is shown in table 1. The algorithm includes the following seven steps. (1) constructing a two-layer association model: the top node is a fault resource, the bottom node is a virtual service, and the connection line from the top node to the bottom node represents that the current fault resource provides network resources for the virtual service connected with the current fault resource. (2) constructing a binary character string of the fault resource. Network node set F using faults n Failed network link set F e Constructing a binary string X i Each bit indicates whether the current network resource is restored. And (3) initializing parameters. From the modeling and analysis of particle swarm, the parameters to be initialized include the iteration number MG of algorithm, particle swarm size N, and initial position X of randomly generated particles i Initial velocity V of randomly generated particles i . (4) calculating an initial position. The objective function of the virtual network service fault recovery problem is equation (5), so equation (5) is set as the fitness function value f (X i ). (5), particle velocity and particle location update. When the virtual network service is restored, the service resource allocation constraint to be satisfied comprises the resource allocation constraint of the bottom layer node and the resource allocation constraint of the bottom layer link. Therefore, when judging whether or not each particle position meets the constraint condition, the constraint condition is set to the formulas (1) to (4), and the corresponding operation is performed. (6) And updating the global optimal initial position and the individual optimal initial position. By passing throughJudging global optimal initial position X gb And an individual optimum initial position X pb And updating the global optimal initial position and the individual optimal initial position. And (7) judging whether the end condition is reached. The judging condition is the maximum iteration number MG; if the maximum iteration number is reached, outputting the optimal X i 。
Table 1 virtual service fault recovery algorithm based on particle swarm
In one embodiment of the present invention, the constructing a fault recovery model in a network slice environment according to the bottom node resources and the bottom link resources of the bottom network in the base network specifically includes:
constructing a resource constraint condition of bottom node recovery, and adopting the following formula:
wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a set of failed nodes that need to be restored, +.>A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When->When the value is 1, it indicates that the failed node m has been successfully recovered, when +.>When the value is 0, the fault node m is not successfully recovered, re n Representing the total node recovery resource amount;
constructing a constraint condition of the recovery resources of the bottom link, and adopting the formula:
wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e A set representing the failed link composition requiring restoration, +.>Identification indicating whether the failed link mn was successfully recovered, with a value of +.>When (when)When the value is 1, it indicates that the failed link mn is successfully recovered, when +.>When the value is 0, the failure link mn is not recovered successfully, re e Representing the total link recovery resource amount;
constructing a constraint condition of allocating resources by the bottom layer node, and adopting the formula:
wherein, representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node->Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The number of computing resources occupied by the virtual service which can still be borne after the fault occurs; / >
Constructing a constraint condition of the allocation resources of the bottom link, and adopting the following formula:
wherein, representing recovered faulty traffic +>The amount of bandwidth resources allocated to the underlying link mn is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link mn, B mn Representing the total bandwidth resource amount of the underlying link mn, B g Indicating that the underlying link mn is still loadable after failureThe amount of bandwidth resources occupied by the virtual service;
establishing an objective function of a fault recovery model according to the resource constraint condition of the bottom node recovery, the resource constraint condition of the bottom link recovery, the resource constraint condition of the bottom node allocation and the resource constraint condition of the bottom link allocation:
wherein, indicating the number of successfully restored virtual network traffic, +.>Representing a failed set of virtual network traffic, +.>Representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When->When the value is 1, the virtual business is represented>Is successfully recovered when->When the value is 0, the virtual business is represented>Is not successfully recovered.
In one embodiment of the present invention, the building of the particle swarm optimization algorithm model according to the fault recovery model specifically includes:
And optimizing the position parameters of the particles and the speed parameters of the particles in the particle swarm algorithm to obtain a particle swarm optimization algorithm model, wherein the position parameters of the particles represent a resource recovery scheme, and the speed of the particles represent an optimization strategy of the resource recovery scheme.
In one embodiment of the present invention, the method adopts the particle swarm optimization algorithm model to solve the fault recovery model to obtain a virtual service fault recovery strategy, which specifically includes:
constructing a two-layer association model of the fault resource and the virtual service according to the mapping relation of the fault resource and the virtual service;
building a binary string X of a failed resource i Each bit indicating whether the current network resource is restored;
initializing parameters, wherein the parameters comprise: iteration number MG, particle swarm size N, initial position X of randomly generated particles i And initial velocity V of randomly generated particles i ;
Calculating an initial position of the particle, comprising: calculating fitness function value f (X) of each particle position i ) And will be the optimal initial position X i Set as global optimum initial position X gb The initial position X of each particle i Set to the individual optimal initial position X pb ;
Updating the particle speed, the particle position, the global optimal initial position and the individual optimal initial position;
Judging whether a preset end condition is reached, if so, outputting the optimal X i If not, returning to the execution step to update the particle speed, the particle position, the global optimal initial position and the individual optimal initial position.
In the experimental environment of the present invention, a GT-ITM tool was used to generate a network topology environment. In the aspect of the bottom network, the number of bottom network nodes is increased from 100 to 700, so as to describe the network environment under different network scale environments. The resources of each underlying node, the resources of each underlying link, are subject to an even distribution (10, 30). In terms of virtual networks, the number of virtual network nodes is subject to a uniform distribution of (10, 30), and the resources of each virtual node and the resources of each virtual link are subject to a uniform distribution of (1, 5). Because the recovery of the bottom link failure and the bottom node failure is similar, the bottom link failure is taken as a research object in the experiment. In simulating the failure of the underlying links, the probability of each link failure is 0.05. When a certain underlying link fails, its remaining link capacity is subject to a uniform distribution of (0, 10).
In terms of algorithm comparison, the inventive algorithm VSFRAoPW is compared to a heuristic recovery algorithm (Heuristic recovery algorithm, VSFRAoHR). The algorithm VSFRAoHR aims at maximizing the recovery fault business quantity, and a particle swarm optimization algorithm is adopted for solving. In the aspect of comparing indexes, two indexes of fault recovery rate and user satisfaction are used for evaluation. The failure recovery rate refers to the ratio of the number of failed virtual network traffic to the total number of virtual network traffic that is successfully recovered. The user satisfaction u is calculated using formula (11). Wherein, flow θ Representing the traffic of the recovered virtual network traffic. f (f) θ Indicating the number of virtual network traffic recovered. Θ represents the set of virtual network traffic that has been successfully recovered. Ω represents a set of virtual network traffic that needs to be restored. Alpha and beta are weight factors that regulate the amount of recovered traffic and the amount of recovered traffic. As can be seen from the formula (11), the more the number and flow of the recovered virtual network services, the larger the numerator of the formula (11), the larger the value of the user satisfaction u, and the better the algorithm recovery effect.
The experimental results of the failure recovery rate are shown in fig. 2. The X-axis indicates that the number of underlay network nodes increases from 100 to 700 for verifying the performance of the algorithm at different underlay network scales. The Y-axis represents recovery rate of virtual network traffic failure. The total amount of the underlying link recovery resources used in the experiment was 300. From the experimental results, as the scale of the underlying network increases, the recovery rate of the virtual network service of both algorithms is reduced. This is because the size of the underlying network increases, the number of failed virtual network traffic increases, and the recovery resources required also increase. In terms of performance analysis of the two algorithms, the recovery rate of the virtual network service fault recovery of the algorithm is higher than that of the comparison algorithm under various network environments. The particle swarm optimization algorithm adopted by the algorithm can better obtain the global optimal solution, thereby improving the recovery success rate of the virtual network service.
The experimental results of recovering the effect of the total amount of resources on user satisfaction are shown in fig. 3. The X-axis in the figure shows that the total amount of recovery resources increases from 100 to 500. The Y-axis represents user satisfaction value. The experimental result shows the user satisfaction condition of the bottom network nodes in the network environment with the number of 400. As can be seen from the figure, as the total amount of recovery resources increases, the user satisfaction under both algorithms increases, because after the total amount of recovery resources increases, more failed underlying network resources can be recovered, thereby recovering more failed virtual network services. As can be seen from the user satisfaction analysis of the two algorithms, the user satisfaction of the algorithm of the invention is higher than that of the comparison algorithm under various environments of recovering the total resources. This is because the algorithm of the present invention can find the optimal restoration policy, thereby restoring more failed virtual traffic.
Compared with the prior art, the virtual service fault recovery method based on the particle swarm under the network slice has the beneficial effects that:
the invention aims at maximizing the recovery fault business quantity and adopts a particle swarm optimization algorithm to solve. In the aspect of comparing indexes, the invention uses two indexes of fault recovery rate and user satisfaction to evaluate, and compared with the existing fault recovery method, the invention can find the optimal recovery strategy by running in the experimental simulation environment, and can recover more failed bottom network resources, thereby recovering more failed virtual network services.
Second embodiment of the present invention:
as shown in fig. 2, a virtual service fault recovery apparatus 200 based on a particle swarm under a network slice according to an embodiment of the present invention includes: a fault construction module 201, an algorithm construction module 202, and a processing module 203, wherein,
the fault construction module 201 is configured to construct a fault recovery model in a network slice environment according to a bottom node resource and a bottom link resource of a bottom network in a base network;
the algorithm construction module 202 is configured to construct a particle swarm optimization algorithm model according to the fault recovery model;
the processing module 203 is configured to solve the fault recovery model by using the particle swarm optimization algorithm model, so as to obtain a virtual service fault recovery strategy.
In one embodiment of the present invention, the fault construction module 201 is specifically configured to:
constructing a resource constraint condition of bottom node recovery, and adopting the following formula:
wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a set of failed nodes that need to be restored, +.>A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When->When the value is 1, it indicates that the failed node m has been successfully recovered, when +. >When the value is 0, the fault node m is not successfully recovered, re n Representing the total node recovery resource amount;
constructing a constraint condition of the recovery resources of the bottom link, and adopting the formula:
wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e A set representing the failed link composition requiring restoration, +.>Identification indicating whether the failed link mn was successfully recovered, with a value of +.>When (when)When the value is 1, it indicates that the failed link mn is successfully recovered, when +.>When the value is 0, the failure link mn is not recovered successfully, re e Representing the total link recovery resource amount;
constructing a constraint condition of allocating resources by the bottom layer node, and adopting the formula:
wherein, representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node->Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The number of computing resources occupied by the virtual service which can still be borne after the fault occurs;
constructing a constraint condition of the allocation resources of the bottom link, and adopting the following formula:
wherein, representing recovered faulty traffic + >The amount of bandwidth resources allocated to the underlying link mn is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link mn, B mn Representing the total bandwidth resource amount of the underlying link mn, B g The bandwidth resource quantity occupied by the virtual service which can still be carried after the bottom link mn fails is represented;
establishing an objective function of a fault recovery model according to the resource constraint condition of the bottom node recovery, the resource constraint condition of the bottom link recovery, the resource constraint condition of the bottom node allocation and the resource constraint condition of the bottom link allocation:
wherein, indicating the number of successfully restored virtual network traffic, +.>Representing a failed set of virtual network traffic, +.>Representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When->When the value is 1, the virtual business is represented>Is successfully recovered when->When the value is 0, the virtual business is represented>Is not successfully recovered.
In one embodiment of the present invention, the algorithm construction module 202 is specifically configured to:
and optimizing the position parameters of the particles and the speed parameters of the particles in the particle swarm algorithm to obtain a particle swarm optimization algorithm model, wherein the position parameters of the particles represent a resource recovery scheme, and the speed of the particles represent an optimization strategy of the resource recovery scheme.
In one embodiment of the present invention, the processing module 203 is specifically configured to:
constructing a two-layer association model of the fault resource and the virtual service according to the mapping relation of the fault resource and the virtual service;
building a binary string X of a failed resource i Each bit indicating whether the current network resource is restored;
initializing parameters, wherein the parameters comprise: iteration number MG, particle swarm size N, initial position X of randomly generated particles i And initial velocity V of randomly generated particles i ;
Calculating an initial position of the particle, comprising: calculating fitness function value f (X) of each particle position i ) And will be the optimal initial position X i Set as global optimum initial position X gb The initial position X of each particle i Set to the individual optimal initial position X pb ;
Updating the particle speed, the particle position, the global optimal initial position and the individual optimal initial position;
judging whether a preset end condition is reached, if so, outputting the optimal X i If not, returning to the execution step to update the particle speed, the particle position, the global optimal initial position and the individual optimal initial position.
Third embodiment of the invention:
the embodiment of the invention also provides a computer terminal device, which comprises: one or more processors;
A memory coupled to the processor for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the method for particle swarm-based virtual traffic failure recovery under network slice as described in any of the preceding claims.
It should be noted that the processor may be a central processing unit (CentralProcessingUnit, CPU), other general purpose processors, digital signal processors (DigitalSignalProcessor, DSP), application specific integrated circuits (ApplicationSpecificIntegratedCircuit, ASIC), off-the-shelf programmable gate arrays (Field-ProgrammableGateArray, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., or any conventional processor that is a control center of the terminal device and that connects various parts of the terminal device using various interfaces and lines.
The memory mainly includes a program storage area, which may store an operating system, an application program required for at least one function, and the like, and a data storage area, which may store related data and the like. In addition, the memory may be a high-speed random access memory, a nonvolatile memory such as a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash memory card (FlashCard), etc., or other volatile solid state memory devices.
It should be noted that the above-mentioned terminal device may include, but is not limited to, a processor, a memory, and those skilled in the art will understand that the above-mentioned terminal device is merely an example, and does not constitute limitation of the terminal device, and may include more or fewer components, or may combine some components, or different components.
Fourth embodiment of the present invention:
the embodiment of the invention also provides a computer readable storage medium, on which a computer program is stored, which is characterized in that the computer program, when executed by a processor, implements the virtual service fault recovery method based on the particle swarm under the network slice as described in any one of the above.
It should be noted that the computer program may be divided into one or more modules/units (e.g., computer program), which are stored in the memory and executed by the processor to accomplish the present invention. The one or more modules/units may be a series of computer program instruction segments capable of performing the specified functions, which instruction segments are used for describing the execution of the computer program in the terminal device.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention, and are not to be construed as limiting the scope of the invention. It should be noted that any modifications, equivalent substitutions, improvements, etc. made by those skilled in the art without departing from the spirit and principles of the present invention are intended to be included in the scope of the present invention.
Claims (8)
1. The virtual service fault recovery method based on the particle swarm under the network slice is characterized by comprising the following steps:
according to the bottom node resources and the bottom link resources of the bottom network in the basic network, a fault recovery model under the network slicing environment is constructed, and the fault recovery model specifically comprises the following steps: constructing a resource constraint condition of bottom node recovery, and adopting the following formula:
wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a set of failed nodes that need to be restored, +.>A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When->When the value is 1, it indicates that the failed node m has been successfully recovered, when +.>When the value is 0, the fault node m is not successfully recovered, re n Representing the total node recovery resource amount;
constructing a constraint condition of the recovery resources of the bottom link, and adopting the formula:
wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e A set representing the failed link composition requiring restoration, +.>Identification indicating whether the failed link mn was successfully recovered, with a value of +.>When->When the value is 1, it indicates that the failed link mn is successfully recovered, when +.>When the value is 0, the failure link mn is not recovered successfully, re e Representing the total link recovery resource amount;
constructing a constraint condition of allocating resources by the bottom layer node, and adopting the formula:
wherein, representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node->Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The number of computing resources occupied by the virtual service which can still be borne after the fault occurs;
constructing a constraint condition of the allocation resources of the bottom link, and adopting the following formula:
wherein, representing recovered faulty traffic +>The amount of bandwidth resources allocated to the underlying link mn is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link mn, B mn Representing the total bandwidth resource amount of the underlying link mn, B g The bandwidth resource quantity occupied by the virtual service which can still be carried after the bottom link mn fails is represented;
establishing an objective function of a fault recovery model according to the resource constraint condition of the bottom node recovery, the resource constraint condition of the bottom link recovery, the resource constraint condition of the bottom node allocation and the resource constraint condition of the bottom link allocation:
Wherein, indicating the number of successfully restored virtual network traffic, +.>Representing the set of failed virtual network traffic,representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When->When the value is 1, the virtual business is represented>Is successfully recovered when->When the value is 0, the virtual business is represented>Is not successfully recovered;
constructing a particle swarm optimization algorithm model according to the fault recovery model;
and solving the fault recovery model by adopting the particle swarm optimization algorithm model to obtain a virtual service fault recovery strategy.
2. The method for recovering virtual service faults based on particle swarm under network slices according to claim 1, wherein the constructing a particle swarm optimization algorithm model according to the fault recovery model is specifically as follows:
and optimizing the position parameters of the particles and the speed parameters of the particles in the particle swarm algorithm to obtain a particle swarm optimization algorithm model, wherein the position parameters of the particles represent a resource recovery scheme, and the speed parameters of the particles represent an optimization strategy of the resource recovery scheme.
3. The method for recovering a virtual service fault based on a particle swarm under a network slice according to claim 1, wherein the method for recovering a virtual service fault based on a particle swarm optimization algorithm model is characterized in that the method for recovering a fault based on a particle swarm optimization algorithm model is adopted to solve the fault recovery model to obtain a virtual service fault recovery strategy, and specifically comprises the following steps:
Constructing a two-layer association model of the fault resource and the virtual service according to the mapping relation of the fault resource and the virtual service;
building a binary string X of a failed resource i Each bit indicating whether the current network resource is restored;
parameters (parameters)Initializing, wherein the parameters comprise: iteration number MG, particle swarm size N, initial position X of randomly generated particles i And initial velocity V of randomly generated particles i ;
Calculating an initial position of the particle, comprising: calculating fitness function value f (X) of each particle position i ) And will be the optimal initial position X i Set as global optimum initial position X gb The initial position X of each particle i Set to the individual optimal initial position X pb ;
Updating the particle speed, the particle position, the global optimal initial position and the individual optimal initial position;
judging whether a preset end condition is reached, if so, outputting the optimal X i If not, returning to the execution step to update the particle speed, the particle position, the global optimal initial position and the individual optimal initial position.
4. A virtual service fault recovery device based on particle swarm under network slice, comprising: a fault construction module, an algorithm construction module and a processing module, wherein,
The fault construction module is used for constructing a fault recovery model in a network slicing environment according to bottom node resources and bottom link resources of a bottom network in the basic network, and is specifically used for:
constructing a resource constraint condition of bottom node recovery, and adopting the following formula:
wherein, representing the amount of node resources needed to be consumed by the fault node m, F n Representing a set of failed nodes that need to be restored, +.>A flag indicating whether the failed node m was successfully recovered, the value of which is +.>When->When the value is 1, it indicates that the failed node m has been successfully recovered, when +.>When the value is 0, the fault node m is not successfully recovered, re n Representing the total node recovery resource amount;
constructing a constraint condition of the recovery resources of the bottom link, and adopting the formula:
wherein, representing the amount of link resources that need to be consumed to recover the failed link mn, F e A set representing the failed link composition requiring restoration, +.>Identification indicating whether the failed link mn was successfully recovered, with a value of +.>When->When the value is 1, it indicates that the failed link mn is successfully recovered, when +.>When the value is 0, the failure link mn is not recovered successfully, re e Representing the total link recovery resource amount;
constructing a constraint condition of allocating resources by the bottom layer node, and adopting the formula:
Wherein, representing recovered faulty traffic +>Requiring an underlying node->The amount of computing resources allocated thereto; c m Representing a malfunctioning bottom node->Remaining computing resource capacity, C m Representing the underlying node->The total number of computing resources, C g Representing the underlying node->The number of computing resources occupied by the virtual service which can still be borne after the fault occurs;
constructing a constraint condition of the allocation resources of the bottom link, and adopting the following formula:
wherein the method comprises the steps of,Representing recovered faulty traffic +>The amount of bandwidth resources allocated to the underlying link mn is required; e, e mn Representing the remaining bandwidth resource capacity of the failed underlying link mn, B mn Representing the total bandwidth resource amount of the underlying link mn, B g The bandwidth resource quantity occupied by the virtual service which can still be carried after the bottom link mn fails is represented;
establishing an objective function of a fault recovery model according to the resource constraint condition of the bottom node recovery, the resource constraint condition of the bottom link recovery, the resource constraint condition of the bottom node allocation and the resource constraint condition of the bottom link allocation:
wherein, indicating the number of successfully restored virtual network traffic, +.>Representing the set of failed virtual network traffic, Representing virtual traffic +.>The sign of whether successfully recovered takes the value +.>When->When the value is 1, the virtual business is represented>Is successfully recovered when->When the value is 0, the virtual business is represented>Is not successfully recovered;
the algorithm construction module is used for constructing a particle swarm optimization algorithm model according to the fault recovery model;
and the processing module is used for solving the fault recovery model by adopting the particle swarm optimization algorithm model to obtain a virtual service fault recovery strategy.
5. The virtual business fault recovery device based on particle swarm under a network slice according to claim 4, wherein the algorithm construction module is specifically configured to:
and optimizing the position parameters of the particles and the speed parameters of the particles in the particle swarm algorithm to obtain a particle swarm optimization algorithm model, wherein the position parameters of the particles represent a resource recovery scheme, and the speed parameters of the particles represent an optimization strategy of the resource recovery scheme.
6. The virtual traffic failure recovery device based on particle swarm under a network slice according to claim 4, wherein the processing module is specifically configured to:
constructing a two-layer association model of the fault resource and the virtual service according to the mapping relation of the fault resource and the virtual service;
Building a binary string X of a failed resource i Each bit indicates whether the current network resource is restoredRepeating;
initializing parameters, wherein the parameters comprise: iteration number MG, particle swarm size N, initial position X of randomly generated particles i And initial velocity V of randomly generated particles i ;
Calculating an initial position of the particle, comprising: calculating fitness function value f (X) of each particle position i ) And will be the optimal initial position X i Set as global optimum initial position X gb The initial position X of each particle i Set to the individual optimal initial position X pb ;
Updating the particle speed, the particle position, the global optimal initial position and the individual optimal initial position;
judging whether a preset end condition is reached, if so, outputting the optimal X i If not, returning to the execution step to update the particle speed, the particle position, the global optimal initial position and the individual optimal initial position.
7. A computer terminal device, comprising:
one or more processors;
a memory coupled to the processor for storing one or more programs;
the one or more programs, when executed by the one or more processors, cause the one or more processors to implement the particle swarm based virtual traffic failure recovery method under a network slice according to any of claims 1 to 3.
8. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a particle swarm based virtual service failure recovery method under a network slice according to any of claims 1 to 3.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110353228.9A CN112953781B (en) | 2021-03-31 | 2021-03-31 | Virtual service fault recovery method and device based on particle swarm under network slice |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110353228.9A CN112953781B (en) | 2021-03-31 | 2021-03-31 | Virtual service fault recovery method and device based on particle swarm under network slice |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112953781A CN112953781A (en) | 2021-06-11 |
CN112953781B true CN112953781B (en) | 2023-04-28 |
Family
ID=76231920
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110353228.9A Active CN112953781B (en) | 2021-03-31 | 2021-03-31 | Virtual service fault recovery method and device based on particle swarm under network slice |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112953781B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116192640A (en) * | 2021-11-25 | 2023-05-30 | 中移(苏州)软件技术有限公司 | Network slice resource allocation method and device, SDN controller and storage medium |
CN115103245A (en) * | 2022-06-24 | 2022-09-23 | 烽火通信科技股份有限公司 | Optical network fault analysis method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108322406A (en) * | 2017-12-28 | 2018-07-24 | 广东电网有限责任公司电力调度控制中心 | A kind of SDN data plane failure restoration methods based on link performance and flow point class |
CN111565146A (en) * | 2020-05-27 | 2020-08-21 | 南方电网调峰调频发电有限公司信息通信分公司 | Network topology aware power communication network link fault recovery algorithm |
CN111682962A (en) * | 2020-05-19 | 2020-09-18 | 南方电网调峰调频发电有限公司信息通信分公司 | Power data network fault recovery method, system and storage medium |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102364899A (en) * | 2011-11-16 | 2012-02-29 | 北京邮电大学 | Particle-swam-optimization-based virtual network mapping method and system |
CN108182498A (en) * | 2018-01-15 | 2018-06-19 | 国网黑龙江省电力有限公司电力科学研究院 | The restorative reconstructing method of distribution network failure |
CN109995028B (en) * | 2019-04-09 | 2023-05-12 | 国网山东省电力公司济南供电公司 | Distribution network fault recovery method and system based on optimal recovery sequence |
CN110350510B (en) * | 2019-05-23 | 2023-04-28 | 国网河南省电力公司郑州供电公司 | Power distribution network power supply recovery method considering fault influence degree |
-
2021
- 2021-03-31 CN CN202110353228.9A patent/CN112953781B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108322406A (en) * | 2017-12-28 | 2018-07-24 | 广东电网有限责任公司电力调度控制中心 | A kind of SDN data plane failure restoration methods based on link performance and flow point class |
CN111682962A (en) * | 2020-05-19 | 2020-09-18 | 南方电网调峰调频发电有限公司信息通信分公司 | Power data network fault recovery method, system and storage medium |
CN111565146A (en) * | 2020-05-27 | 2020-08-21 | 南方电网调峰调频发电有限公司信息通信分公司 | Network topology aware power communication network link fault recovery algorithm |
Also Published As
Publication number | Publication date |
---|---|
CN112953781A (en) | 2021-06-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112953781B (en) | Virtual service fault recovery method and device based on particle swarm under network slice | |
Alicherry et al. | Network aware resource allocation in distributed clouds | |
US9342370B2 (en) | Server migration | |
Blenk et al. | Boost online virtual network embedding: Using neural networks for admission control | |
CN112153700A (en) | Network slice resource management method and equipment | |
CN108667657B (en) | SDN-oriented virtual network mapping method based on local feature information | |
CN111682962B (en) | Power data network fault recovery method, system and storage medium | |
CN110414569A (en) | Cluster realizing method and device | |
CN112312444B (en) | Resource backup method under 5G network slice | |
CN115358487A (en) | Federal learning aggregation optimization system and method for power data sharing | |
Candan et al. | A dynamic island model for adaptive operator selection | |
EP4167540A1 (en) | Availability slo-aware network optimization | |
CN111160661B (en) | Method, system and equipment for optimizing reliability of power communication network | |
Levitin | Optimal structure of multi-state systems with uncovered failures | |
US9565101B2 (en) | Risk mitigation in data center networks | |
Yang et al. | Trust-based scheduling strategy for cloud workflow applications | |
CN115361295B (en) | TOPSIS-based resource backup method, device, equipment and medium | |
CN115001978B (en) | Cloud tenant virtual network intelligent mapping method based on reinforcement learning model | |
Al Jadaan et al. | Enhancing data selection using genetic algorithm | |
CN112787833A (en) | Method and device for deploying CDN (content delivery network) server | |
CN113572639B (en) | Carrier network fault diagnosis method, system, equipment and medium | |
Shojaei et al. | A Pareto-algebraic framework for signal power optimization in global routing | |
JP6732927B2 (en) | Housing form searching apparatus, housing form searching method and program | |
CN115378817B (en) | Resource backup method, device, equipment and storage medium of service function chain | |
CN112181694B (en) | Cloud computing network maintenance reliability analysis method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |